Toward Automated Land Cover Classification in Landsat Images Using Spectral Slopes at Different Bands

For last two decades, various techniques have been advanced for classification of satellite imageries. A vast majority of them are supervised/semisupervised requiring manual selection of samples for each class. Some of the unsupervised approaches are based on hard thresholds and particular to image...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2017-03, Vol.10 (3), p.1096-1104
Main Authors: Aswatha, Shashaank M., Mukherjee, Jayanta, Biswas, Prabir K., Aikat, Subhas
Format: Article
Language:English
Subjects:
Agricultural land
Classification
Cluster analysis
Clustering
Earth
Image acquisition
Image classification
Indexes
Land cover
Landsat
Landsat satellites
Normalized spectral indices
Remote sensing
satellite image classification
Satellite imagery
Satellites
Slope
Slopes
Spectra
spectral slopes
Support vector machines
temporal scene change analysis
Training
Vector quantization
Vegetation
Vegetation mapping
Wavelength
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For last two decades, various techniques have been advanced for classification of satellite imageries. A vast majority of them are supervised/semisupervised requiring manual selection of samples for each class. Some of the unsupervised approaches are based on hard thresholds and particular to image acquisition modules. In this study, we propose a spectral-slope-based classification technique and subsequently summarize the changes in temporal image sets. Using the properties of spectral slopes, we propose a set of rules for selection of training samples from Landsat imageries for classifying the land cover. The images are initially classified into three classes: water, vegetation, and vegetation-void. Further, vegetation and vegetation-void regions are classified into proper vegetation and dry cropland, and urban land and bare land, respectively. The initial classification is performed by support vector machines, and the second-level classification is performed through k-means clustering and subsequent labeling of clusters to subclasses. Considering temporal images of the same scene, postclassification change summarization is carried out to quantize the land variations, both qualitatively (type of change) and quantitatively (volume of change).The approach has been used in the analysis of images acquired by different sensors operating under similar wavelength ranges.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2016.2602390